INDEX

Explanations

technical and programming terms related to functionality

oai_token-act-pair · gpt-3.5-turbo

references to the concept of "function" in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

cott

-0.87

pee

-0.70

creen

-0.68

yu

-0.65

 Hemp

-0.65

Jed

-0.64

bows

-0.63

lake

-0.63

chu

-0.62

 Lank

-0.62

POSITIVE LOGITS

ality

1.14

ional

1.04

alities

0.95

aries

0.94

ative

0.93

ivity

0.84

ioned

0.84

inic

0.83

icular

0.81

istry

0.80

Activations Density 0.037%

technical and programming terms related to functionality

references to the concept of "function" in various contexts

No Comments

No Known Activations